DeepSeek V3.1 Terminus API pricing
DeepSeek · Budget price tier · MIT · released 2025-09. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $90.50 on DeepSeek V3.1 Terminus; the next cheaper model in the Budget price tier for this workload, Codestral 2508, does it for $90.00. The price we quote for DeepSeek V3.1 Terminus has changed 3 times since 2026-08-15, most recently on 2026-10-03 when the quoted host changed (-1.1%); it is now the 113th cheapest of 160 models in the Budget price tier. Only one host, SiliconFlow, sells it, so there is no second price to shop. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.27 per 1M tokens
- Output: $1.00 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: Not published
- Context window: 164K tokens
- Arena ELO: 1417 as of 2026-11-08
Market position
On blended price ($0.781 per 1M tokens at 30% input, 70% output) it is cheaper than 30% of models in the Budget price tier: 113th cheapest of 160. Across every price tier it is cheaper than 63% of priced text models in the catalogue: 113th cheapest of 303. Its Arena ELO of 1417 ranks 82nd of the 160 models that carry one, tied with 3 others, above 47% of them. With an Arena score of 1417, DeepSeek V3.1 Terminus sits below OptimNow's lowest working quality threshold, Standard (Arena 1420+), so the quality-bar method would not shortlist it for any of the 8 use cases the table prices. It is 3 points under the Standard bar (Arena 1420+), within the benchmark's 20-point noise. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
DeepSeek V3.1 Terminus is open source: its weights are published under MIT, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its parameter count is not published. Listed capabilities: Text, Reasoning, Agents. Filling its 164K context window once costs $0.0443 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 1 host. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
SiliconFlow is the only host with a published rate, $0.27 input / $1.00 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| SiliconFlow (price we quote) | $0.27 | $1.00 | fp8 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where DeepSeek publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $91 |
| Knowledge Q&A | 2,000 / 800 | $134 |
| Meeting Summary | 10,000 / 1,200 | $390 |
| Marketing Content | 2,500 / 1,800 | $247 |
| Coding Task | 3,000 / 2,000 | $281 |
| Invoice Processing | 1,500 / 600 | $101 |
| Call Summary | 2,000 / 700 | $124 |
| Agent Workflow | 6,000 / 3,000 | $462 |
Price history
DeepSeek V3.1 Terminus has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.27 input / $0.95 output per 1M tokens. The price we quote has changed 3 times since then, 2 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-03, was -1.1% on the blended price (30% input, 70% output), to $0.27 input / $1.00 output (quoted host changed, not a repricing). Net of all changes, the blended price is +4.7% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-10-03 | $0.30 / $1.00 | $0.27 / $1.00 | -1.1% (quoted host changed, not a repricing) |
| 2026-09-29 | $0.27 / $1.00 | $0.30 / $1.00 | +1.2% (quoted host changed, not a repricing) |
| 2026-08-19 | $0.27 / $0.95 | $0.27 / $1.00 | +4.7% |
Alternatives to DeepSeek V3.1 Terminus
2 of the 4 comparable models below cost less than DeepSeek V3.1 Terminus: Qwen3 235B A22B Instruct 2507 undercuts it by 23%, and scores 2 Arena points higher.
- Next cheaper model in the Budget price tier: Qwen3.5-35B-A3B (Alibaba) at $0.742 blended, 5% less.
- Next more expensive: Qwen3 VL 30B A3B Thinking (Alibaba) at $0.787 blended, 1% more.
The nearest models in the Budget price tier on Arena ELO, each with its blended price and score difference against DeepSeek V3.1 Terminus.
- Qwen3 Next 80B A3B Instruct (Alibaba): $0.09 in / $1.10 out per 1M, Arena ELO 1417 (2% more expensive, same Arena ELO)
- Qwen3 235B A22B Instruct 2507 (Alibaba): $0.14 in / $0.80 out per 1M, Arena ELO 1419 (23% cheaper, 2 ELO points higher)
- Qwen3 VL 235B A22B Instruct (Alibaba): $0.21 in / $1.90 out per 1M, Arena ELO 1420 (78% more expensive, 3 ELO points higher)
- DeepSeek V3.1 (DeepSeek): $0.25 in / $0.95 out per 1M, Arena ELO 1420 (5% cheaper, 3 ELO points higher)
- Cheapest within 15 Arena points: DeepSeek V4 Flash 0423 (DeepSeek), 80% cheaper, 15 ELO points higher, out of 33 models in that band.
- Highest Arena ELO within 20% of this price: MiMo-V2.6-Pro (Xiaomi), 5% cheaper, 75 ELO points higher, out of 22 models in that price band.
Other models from DeepSeek
The 8 nearest to DeepSeek V3.1 Terminus in price, of 13 other DeepSeek models in the catalogue. Prices per 1M tokens, input then output.
- DeepSeek V3.2 Exp: $0.27 / $0.41
- DeepSeek V4.1 Flash 1017: $0.15 / $0.60
- DeepSeek V3: $0.32 / $0.89
- DeepSeek V3.1: $0.25 / $0.95
- DeepSeek V3 0324: $0.29 / $1.14
- DeepSeek V4 Flash Vision Exp: $0.44 / $1.32
- DeepSeek V4 Pro 0423: $0.9553 / $1.9105
- R1 0528: $0.50 / $2.15
All 14 DeepSeek models and prices
Common questions about DeepSeek V3.1 Terminus pricing
- How much does DeepSeek V3.1 Terminus cost?
- DeepSeek V3.1 Terminus costs $0.27 per 1M input tokens and $1.00 per 1M output tokens at SiliconFlow, the host whose rate we quote. SiliconFlow serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-12.
- Which host is cheapest for DeepSeek V3.1 Terminus?
- SiliconFlow is the only host with a published rate, $0.27 input / $1.00 output per 1M tokens, which is the price we quote. It serves a quantized fp8 build, which is not the same product as the full-precision model. Host rates as listed on 2026-11-12.
- Does DeepSeek V3.1 Terminus offer batch or cached pricing?
- No. Neither a batch rate nor a prompt-cache rate is published for DeepSeek V3.1 Terminus as of 2026-11-12.
- What would DeepSeek V3.1 Terminus cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $91 on DeepSeek V3.1 Terminus at the list price quoted on 2026-11-12.
- Can DeepSeek V3.1 Terminus be self-hosted?
- Yes. DeepSeek V3.1 Terminus is open source: its weights are published under MIT, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of DeepSeek V3.1 Terminus changed?
- DeepSeek V3.1 Terminus has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.27 input / $0.95 output per 1M tokens. The price we quote has changed 3 times since then, 2 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-03, was -1.1% on the blended price (30% input, 70% output), to $0.27 input / $1.00 output (quoted host changed, not a repricing). Net of all changes, the blended price is +4.7% against 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server